检索说明

  • 查询:GraphRAG evidence retrieval
  • 年份过滤:2025-
  • 单查询上限:20
  • 发现日期:2026-11-12

Semantic Scholar 候选元数据

  • 作者:Yi-Ning Tang, Jun-Yu Zhang, Hao-Miao Qiu, Yong-Chao Liu, Jia-Jun Zheng, Zhao Wang, Zi-Yue Qiao, Chao Wu
  • 年份:2026
  • Venue:未返回
  • DOI:未返回
  • arXiv:2610.19549
  • S2 citationCount(当前快照):0
  • 来源线索:https://arxiv.org/abs/2610.19549

摘要(未核验)

Graph retrieval-augmented generation (GraphRAG) uses document-derived knowledge graphs to assemble evidence for large language model (LLM) answers. Its security depends on both the seed chunks retrieved for a query and the graph evidence assembled from them, yet attacks on this evidence path remain underexplored. We introduce GraphRAG-LTM, a Layered Threat Modeling framework that tests three nested levels of attacker access. BB Query uses ranking feedback to make query edits under a semantic-similarity constraint and demote relevant seed chunks. WB Query uses retriever gradients for the same objective. Graph-aware WB keeps the white-box adversarial query and deletes bridge triplets from the query-specific evidence graph, disrupting multi-hop evidence propagation through localized graph edits. Across datasets, retrievers, and LLM backbones, rank feedback alone reduces answer quality, gradient access strengthens query attacks, and bridge-triplet deletion further impairs supporting-fact retrieval. Further analyses show how seed retrieval and graph evidence jointly contribute to these failures.

转为正式文献前的核验清单

  • [ ] 从论文、出版社、会议、ACL Anthology、OpenReview 或 arXiv 页面核对标题、作者、年份和版本。
  • [ ] 核对 DOI、venue、正式链接和是否存在撤稿/版本变化。
  • [ ] 阅读正文后补充方法、证据边界、结果和与现有研究的关系。

Semantic Scholar 记录用于发现候选,不是正式一手引文,也不支持对结果覆盖范围或研究质量的穷尽性判断。